SVMs and logistic regression

Moderator: Statistisches Maschinelles Lernen

Benutzeravatar
sqrt(2)
Sonntagsinformatiker
Sonntagsinformatiker
Beiträge: 202
Registriert: 12. Apr 2015 11:35

SVMs and logistic regression

Beitrag von sqrt(2) »

Hello,

after a revision of the slides the relationship between lambda in logistic regression and C in SVMs is still not clear for me. Has someone an idea?

mProg
BASIC-Programmierer
BASIC-Programmierer
Beiträge: 147
Registriert: 25. Apr 2015 00:10

Re: SVMs and logistic regression

Beitrag von mProg »

C = 1/lambda
In SVM Error function you delete the 1/m and replace 1/lambda with C by making it a factor to the first part of your equation instead of the second part in logistic regression. In my opinion and due to Andrew Nq(https://www.youtube.com/watch?v=hCOIMkcsm_g) it does make any difference. You can watch the lecture video in the link where this is explained very well (especially after 10:00)

Antworten

Zurück zu „Statistisches Maschinelles Lernen“